Results 11 to 20 of about 1,006,138 (295)

Dynamic Contextualized Word Embeddings [PDF]

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 2021
Static word embeddings that represent words by a single vector cannot capture the variability of word meaning in different linguistic and extralinguistic contexts. Building on prior work on contextualized and dynamic word embeddings, we introduce dynamic contextualized word embeddings that represent words as a function of both linguistic and ...
Hofmann, V, Pierrehumbert, JB, Schütze, H   +2 more
core   +6 more sources

AutoExtend: Combining Word Embeddings with Semantic Resources

Computational Linguistics, 2017
We present AutoExtend, a system that combines word embeddings with semantic resources by learning embeddings for non-word objects like synsets and entities and learning word embeddings that incorporate the semantic information from the resource.
Sascha Rothe, Hinrich Schütze
doaj   +3 more sources

Deterministic Compression of Word Embeddings

IEEE Access
Word embeddings are an indispensable technology in the field of artificial intelligence, particularly when working with natural language processing models.
Yuki Nakamura, Jun Suzuki, Takumi Ito, Kentaro Inui   +3 more
doaj   +3 more sources

Bias in word embeddings [PDF]

Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, 2020
Word embeddings are a widely used set of natural language processing techniques that map words to vectors of real numbers. These vectors are used to improve the quality of generative and predictive models. Recent studies demonstrate that word embeddings contain and amplify biases present in data, such as stereotypes and prejudice.
Orestis Papakyriakopoulos, Simon Hegelich, Juan Carlos Medina Serrano, Fabienne Marco   +3 more
openaire   +1 more source

The Impact of Arabic Diacritization on Word Embeddings [PDF]

, 2023
Word embedding is used to represent words for text analysis. It plays an essential role in many Natural Language Processing (NLP) studies and has hugely contributed to the extraordinary developments in the field in the last few years.
Wen, X.B., Xianbin Wen, Mohamed Abbache, Abbache, M., Jingwen Xu, Abbache, A., Xu, J.W., Ahmed Abbache, Meziane, F., Farid Meziane   +9 more
core   +1 more source

Morphological Word-Embeddings [PDF]

Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2015
Published at NAACL ...
Ryan Cotterell, Hinrich Schütze
openaire   +2 more sources

Relational Word Embeddings [PDF]

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019
While word embeddings have been shown to implicitly encode various forms of attributional knowledge, the extent to which they capture relational information is far more limited. In previous work, this limitation has been addressed by incorporating relational knowledge from external knowledge bases when learning the word embedding.
José Camacho-Collados, Luis Espinosa Anke, Steven Schockaert   +2 more
openaire   +4 more sources

Word Embeddings as Statistical Estimators. [PDF]

Sankhya Ser B
Word embeddings are a fundamental tool in natural language processing. Currently, word embedding methods are evaluated on the basis of empirical performance on benchmark data sets, and there is a lack of rigorous understanding of their theoretical properties.
Dey N, Singer M, Williams JP, Sengupta S.   +3 more
europepmc   +5 more sources

Domain-Specific Word Embeddings with Structure Prediction [PDF]

, 2023
Complementary to finding good general word embeddings, an important question for representation learning is to find dynamic word embeddings, for example, across time or domain. Current methods do not offer a way to use or predict information on structure
David Lassner, Shinichi Nakajima, Nakajima, Shinichi, Anne Baillot, Brandl, Stephanie, Baillot, Anne, Lassner, David, Stephanie Brandl   +7 more
core   +1 more source

Attention Word Embedding [PDF]

Proceedings of the 28th International Conference on Computational Linguistics, 2020
Word embedding models learn semantically rich vector representations of words and are widely used to initialize natural processing language (NLP) models. The popular continuous bag-of-words (CBOW) model of word2vec learns a vector embedding by masking a given word in a sentence and then using the other words as a context to predict it.
Shashank Sonkar, Andrew E. Waters, Richard G. Baraniuk   +2 more
openaire   +3 more sources